Augmentation of Heat Transfer Over Dimple Surface in Forced Convection—An RSM and ANN Modelling Approach

The dimples are most commonly used in electronic cooling devices to enhance the transfer of heat. The fluid flow features of non-uniform radius circular dimples with two different arrangements were analyzed in this paper. The testing was performed with air as the cooling medium in laminar forced convection constraints. For various inlet air flow speeds, the average Nusselt numbers and overall heat transfer for various dimple configurations were recorded. In comparison to the first case, the heat transfer rate and heat transfer coefficient were found to be large for the surface with the dimple radius decreasing in the direction of flow (Case b). For prediction, an artificial neural network (ANN) was employed. The sigmoid function yielded the best results. The findings also demonstrated that RSM and ANN were excellent modelling techniques, with good accuracy. In addition, ANN prediction performance was somewhat better than RSM prediction performance.